Audio8-TTS-Preview-0.6b is a compact open-weight text-to-speech model hosted on Hugging Face that achieves state-of-the-art performance at a small scale. It supports multilingual synthesis and zero-shot voice cloning. The model is built with the Transformers library and is intended for developers integrating high-quality, customizable speech generation into applications.
Audio8 TTS Preview 0.6b is a Voice, TTS & speech project. It focuses on running high-quality multilingual TTS and voice cloning without needing massive models or proprietary services. It is built as an open-source project for developers and AI researchers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
It is developed by Audio8, and it first shipped in 2026. The project is developed in the open on GitHub with 75 stars and 17 commits in the last 90 days. Among its 3 catalogued features are Multilingual TTS, Zero-shot Voice Cloning, and Compact Model. Audio8 TTS Preview 0.6b is currently in beta.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do